SwiftMR is a stand-alone software solution intended to be used for acceptance, enhancement and transfer of all body parts MR images in DICOM format. It can be used for noise reduction and increasing image sharpness for MR images. SwiftMR is not intended for use on mobile devices.

Device Description

SwiftMR, is software used as a Medical Device (SaMD) consisting of a software algorithm that enhances images taken by MRI scanners. The device only processes DICOM images for the end User and is intended to be used by radiology technologists in an imaging center, clinic, or hospital. The device's inputs are MRI images in DICOM format. The deep learning algorithm produces enhanced images as outputs with reduced noise and increased sharpness in DICOM format. The deep learning algorithm performs noise reduction with the ability of adjusting the denoising level 0 to level 8, and sharpening filter performs the sharpening function with the ability of adjusting the sharpness level from level 0 to level 5. SwiftMR provides an automatic image quality enhancement function for MR images acquired in various environments. SwiftMR can only be used for professional purposes and is not intended for use on mobile devices.

AI/ML Overview

Here is the requested information about the acceptance criteria and study proving the device meets them:

Acceptance Criteria and Device Performance

Metric	Acceptance Criteria	Reported Device Performance
Noise Reduction	Signal-to-noise ratio (SNR) of SwiftMR-processed images is increased by 40% or more for at least 90% of the dataset for level 1, with an incremental 1% increase per each level.	The test passed, indicating the device met or exceeded this criterion.
Sharpness Increase	Full Width at Half Maximum (FWHM) of a selected region of interest (ROI) is decreased by: - 0.13% (deep learning model) - 0.43% (filter level 1) - 1.7% (filter level 2) - 2.3% (filter level 3) - 3.6% (filter level 4) - 4.5% (filter level 5) for at least 90% of the dataset.	The test passed, indicating the device met or exceeded these criteria.

Study Details

Sample size used for the test set and the data provenance:
- Sample Size: Not explicitly stated as a single number for the entire test set. However, the validation dataset included retrospective clinical images covering a wide range of conditions.
- Data Provenance: Retrospective clinical images from various manufacturers (SIEMENS, GE, PHILIPS, CANON, ESAOTE, FONAR, FUJIFILM), field strengths (0.25T, 0.6T, 1.5T, 3.0T), anatomical regions (Body, Cardiac, Neuro, Musculoskeletal), and protocols (T1, T2, T2*, FLAIR, PD, DWI, MRA). Demographics included adults (22-93 yrs, 88.4%) and pediatrics (0-21 yrs, 11.6%), with 44.8% male and 55.2% female. The dataset also included images with up to 50% time reduction for reduced scan time images. Importantly, the validation dataset included data from sources not included in the training dataset to demonstrate performance is not hindered by site variability.
Number of experts used to establish the ground truth for the test set and the qualifications of those experts: Not specified in the provided document. The document describes quantitative metrics (SNR increase, FWHM decrease) as acceptance criteria, suggesting a technical ground truth rather than expert interpretation of a specific condition.
Adjudication method for the test set: Not applicable based on the description. The acceptance criteria are based on objective, quantitative measurements (SNR and FWHM changes) derived from the image processing algorithm itself, rather than subjective expert consensus.
If a multi-reader multi-case (MRMC) comparative effectiveness study was done, If so, what was the effect size of how much human readers improve with AI vs without AI assistance: An MRMC comparative effectiveness study is not mentioned as part of the validation for this 510(k) submission. The validation focuses on the standalone performance of the algorithm in enhancing image quality based on objective metrics.
If a standalone (i.e., algorithm only without human-in-the-loop performance) was done: Yes, the performance tests described (noise reduction and sharpness increase) assess the standalone performance of the SwiftMR algorithm. The device "only processes DICOM images for the end User" and "performs image processing in the background automatically."
The type of ground truth used (expert consensus, pathology, outcomes data, etc.): The ground truth for the performance validation appears to be technical/quantitative metrics (SNR and FWHM measurements) derived from the images themselves, rather than clinical outcomes, pathology, or direct expert consensus on diagnostic accuracy. The aim is to demonstrate that the device effectively reduces noise and increases sharpness as measured objectively.
The sample size for the training set: Not specified in the provided document.
How the ground truth for the training set was established: Not specified in the provided document. The algorithm uses a deep learning model, and its parameters were "obtained through an image guided optimization process," but the specifics of the training data's ground truth (e.g., if it involved artificially generated noise, paired noisy/clean images, or expert-labeled image quality) are not detailed.

Summary

{0}------------------------------------------------

October 27, 2023

Image /page/0/Picture/1 description: The image shows the logo of the U.S. Food and Drug Administration (FDA). On the left is the Department of Health & Human Services logo. To the right of that is the FDA logo, which is a blue square with the letters "FDA" in white. To the right of the FDA logo is the text "U.S. FOOD & DRUG ADMINISTRATION" in blue.

AIRS Medical Inc. % Jihyeon Seo Head of RA 13-14F, Keungil Tower, 223, Teheran-ro, Gangnam-gu Seoul, 06142, Republic of Korea

Re: K230854

Trade/Device Name: SwiftMR Regulation Number: 21 CFR 892.2050 Regulation Name: Medical Image Management And Processing System Regulatory Class: Class II Product Code: LLZ Dated: September 28, 2023 Received: September 28, 2023

Dear Jihyeon Seo:

We have reviewed your section 510(k) premarket notification of intent to market the device referenced above and have determined the device is substantially equivalent (for the indications for use stated in the enclosure) to legally marketed predicate devices marketed in interstate commerce prior to May 28, 1976, the enactment date of the Medical Device Amendments, or to devices that have been reclassified in accordance with the provisions of the Federal Food, Drug, and Cosmetic Act (the Act) that do not require approval of a premarket approval application (PMA). You may, therefore, market the device, subject to the general controls provisions of the Act. Although this letter refers to your product as a device, please be aware that some cleared products may instead be combination products. The 510(k) Premarket Notification Database available at https://www.accessdata.fda.gov/scripts/cdrb/cfdocs/cfpmn/pmn.cfm identifies.combination product submissions. The general controls provisions of the Act include requirements for annual registration, listing of devices, good manufacturing practice, labeling, and prohibitions against misbranding and adulteration. Please note: CDRH does not evaluate information related to contract liability warranties. We remind you, however, that device labeling must be truthful and not misleading.

If your device is classified (see above) into either class II (Special Controls) or class III (PMA), it may be subject to additional controls. Existing major regulations affecting your device can be found in the Code of Federal Regulations, Title 21, Parts 800 to 898. In addition, FDA may publish further announcements concerning your device in the Federal Register.

Additional information about changes that may require a new premarket notification are provided in the FDA guidance documents entitled "Deciding When to Submit a 510(k) for a Change to an Existing Device" (https://www.fda.gov/media/99812/download) and "Deciding When to Submit a 510(k) for a Software Change to an Existing Device" (https://www.fda.gov/media/99785/download).

{1}------------------------------------------------

Your device is also subject to, among other requirements, the Quality System (QS) regulation (21 CFR Part 820), which includes, but is not limited to, 21 CFR 820.30, Design controls; 21 CFR 820.90, Nonconforming product; and 21 CFR 820.100, Corrective and preventive action. Please note that regardless of whether a change requires premarket review, the QS regulation requires device manufacturers to review and approve changes to device design and production (21 CFR 820.30 and 21 CFR 820.70) and document changes and approvals in the device master record (21 CFR 820.181).

Please be advised that FDA's issuance of a substantial equivalence determination does not mean that FDA has made a determination that your device complies with other requirements of the Act or any Federal statutes and regulations administered by other Federal agencies. You must comply with all the Act's requirements, including, but not limited to: registration and listing (21 CFR Part 807); labeling (21 CFR Part 801); medical device reporting of medical device-related adverse events) (21 CFR Part 803) for devices or postmarketing safety reporting (21 CFR Part 4, Subpart B) for combination products (see https://www.fda.gov/combination-products/guidance-regulatory-information/postmarketing-safety-reportingcombination-products); good manufacturing practice requirements as set forth in the quality systems (QS) regulation (21 CFR Part 820) for devices or current good manufacturing practices (21 CFR Part 4, Subpart A) for combination products; and, if applicable, the electronic product radiation control provisions (Sections 531-542 of the Act); 21 CFR Parts 1000-1050.

Also, please note the regulation entitled, "Misbranding by reference to premarket notification" (21 CFR 807.97). For questions regarding the reporting of adverse events under the MDR regulation (21 CFR Part 803), please go to https://www.fda.gov/medical-device-safety/medical-device-reportingmdr-how-report-medical-device-problems.

For comprehensive regulatory information about mediation-emitting products, including information about labeling regulations, please see Device Advice (https://www.fda.gov/medicaldevices/device-advice-comprehensive-regulatory-assistance) and CDRH Learn (https://www.fda.gov/training-and-continuing-education/cdrh-learn). Additionally, you may contact the Division of Industry and Consumer Education (DICE) to ask a question about a specific regulatory topic. See the DICE website (https://www.fda.gov/medical-device-advice-comprehensive-regulatoryassistance/contact-us-division-industry-and-consumer-education-dice) for more information or contact DICE by email (DICE@fda.hhs.gov) or phone (1-800-638-2041 or 301-796-7100).

Sincerely,

Samul for

Daniel Krainak, Ph.D. Assistant Director Magnetic Resonance and Nuclear Medicine Team DHT8C: Division of Radiological Imaging and Radiation Therapy Devices OHT8: Office of Radiological Health Office of Product Evaluation and Quality Center for Devices and Radiological Health

{2}------------------------------------------------

Indications for Use

510(k) Number (if known) K230854

Device Name SwiftMR

Indications for Use (Describe)

Type of Use (Select one or both, as applicable)
Prescription Use (Part 21 CFR 801 Subpart D)	Over-The-Counter Use (21 CFR 801 Subpart C)

CONTINUE ON A SEPARATE PAGE IF NEEDED.

This section applies only to requirements of the Paperwork Reduction Act of 1995.

DO NOT SEND YOUR COMPLETED FORM TO THE PRA STAFF EMAIL ADDRESS BELOW.

The burden time for this collection of information is estimated to average 79 hours per response, including the time to review instructions, search existing data sources, gather and maintain the data needed and complete and review the collection of information. Send comments regarding this burden estimate or any other aspect of this information collection, including suggestions for reducing this burden, to:

Department of Health and Human Services Food and Drug Administration Office of Chief Information Officer Paperwork Reduction Act (PRA) Staff PRAStaff(@fda.hhs.gov

"An agency may not conduct or sponsor, and a person is not required to respond to, a collection of information unless it displays a currently valid OMB number."

{3}------------------------------------------------

Image /page/3/Picture/1 description: The image shows the logo for AIRS Medical. The logo consists of a large, blue letter "A" with a horizontal line extending from the right side of the "A". To the right of the "A" are the words "AIRS" and "MEDICAL" stacked on top of each other. The words "AIRS" and "MEDICAL" are in black.

This 510(k) Summary of safety and effectiveness information is being submitted in accordance with the requirements of 21 CFR 807.92.

I. SUBMITTER

Mrs. Jihyeon Seo Head of RA AIRS Medical Inc. 13-14F, Keungil Tower, 223, Teheran-ro, Gangnam-gu, Seoul, 06142, Republic of Korea Phone: +82-70-7777-3186 FAX: +82-2-6280-3185 Email: seo.kate@airsmed.com

Date Prepared: March 28, 2023

II. DEVICE

Name of Device: SwiftMR Common or Usual Name: Medical Image Management and Processing System Classification Name: system, image processing, radiological (21 CFR 892.2050) Requlatory Class: II Product Code: LLZ

III. PREDICATE DEVICE

Primary Predicate Device: SwiftMR - K220416 by AIRS Medical, Inc., Class II, CFR 892.2050, classification with product code LLZ.

IV. DEVICE DESCRIPTION

The device's inputs are MRI images in DICOM format. The deep learning algorithm produces enhanced images as outputs with reduced noise and increased sharpness in DICOM format. The deep learning algorithm performs noise reduction with the ability of adjusting the denoising level 0 to level 8, and sharpening filter performs the sharpening function with the ability of adjusting the sharpness level from level 0 to level 5.

SwiftMR provides an automatic image quality enhancement function for MR images acquired in various environments. SwiftMR can only be used for professional purposes and is not intended for use on mobile devices.

SwiftMR 's automation procedure is as follows:

. Receive MR images that are in DICOM format from PACS or from MRI
Image quality enhancement using Deep Learning model and sharpening . filter
Transfer enhanced MR image as DICOM format to PACS or to MRI .

There is one deep learning model that can be applied to images from any MRIs with field strength of 0.25T, 0.6T, 1.5T, 3.0T. After integration with the facilities PACS. SwiftMR performs image processing in the background automatically. At

{4}------------------------------------------------

Image /page/4/Picture/0 description: The image shows the logo for AIRS Medical. The logo consists of a large blue letter "A" with a curved line extending from the middle of the left side of the "A". To the right of the "A" are the words "AIRS" and "MEDICAL" stacked on top of each other in black font. The logo is simple and modern, and the use of blue and black gives it a professional look.

the same time. SwiftMR allows logged-in users to use its functions and view the processing status. When logged in as the System Admin, the function is available to the control automation procedure and system change settings. On the User side. the User can retrieve the results of image processing in the form of a worklist by login to the user account.

The software provides three main functions, which are image processing, quality check and progress monitoring.

The software is intended to run automatically in the background so that it does not interrupt the workflow of users. When the user executes MR scans as he/she usually does, the newly acquired images are automatically uploaded to the server and registered in the database (DB) for image processing. Once image processing is complete, the images are sent to PACS or to MR device.

If the user wishes to monitor this automated workflow to check on the status of image processing, he/she can check the main page of the client application or toast messages will appear on the bottom right corner upon completion of each processing. After using the software, they should log out for security reasons.

A settings menu is provided in the form of a user interface to enable system admin to modify software settings as required by the institution or respective user.

V. INDICATIONS FOR USE

SwiftMR is not intended for use on mobile devices.

VI. COMPARISON OF TECHNOLOGICAL CHARACTERISTICS WITH THE PREDICATE DEVICES

The subject device and the predicate device are substantially equivalent in the areas of general function, application, and intended use.

Any differences between the predicate and the subject device have no negative impact on the device safety or efficacy and does not raise any new potential or increased safety risks and is equivalent in performance to existing legally marketed devices.

Item	Predicate Device(SwiftMR (K220416))	Subject Device(SwiftMR)	Differences
PhysicalCharacteristics	Software device thatoperates on off-the-shelf computerhardware	Same as predicate	No Difference
Computer	PC Compatible	Same as predicate	No Difference
DICOMStandardCompliance	The software processesDICOM-compliantimage data	Same as predicate	No Difference
Item	Predicate Device(SwiftMR (K220416))	Subject Device(SwiftMR)	Differences
Modalities	MRI	Same as predicate	No Difference
ImageEnhancementAlgorithmDescription	SwiftMR implements animage enhancementalgorithm usingconvolutionalneural network-basedfiltering. Originalimages are enhancedby running through acascade offilter banks, wherethresholding andscaling operations areapplied. Neuralnetwork-based filtersthat perform noisereduction are obtained.The parameters of thefilters were obtainedthrough an imageguided optimizationprocess.Sharpening filter isadditionally applied tothe deep learningprocessed image.	SwiftMR implements animage enhancementalgorithm usingconvolutionalneural network-basedfiltering. Originalimages are enhancedby running through acascade offilter banks, wherethresholding andscaling operations areapplied. Neuralnetwork-based filtersthat perform noisereduction and/orsharpening areobtained. Theparameters of the filterswere obtained throughan image guidedoptimization process.Sharpening filter isadditionally applied tothe deep learningprocessed image.	The deep learning model alsoperforms sharpening function.
Deep learningmodels	3 General sequencemodels1 TOF sequence model	1 model	The deep learning model is appliedfor all types of images (including butnot limited to T1, T2, T2*, PD,FLAIR, DWI, MRA).
Supported bodyparts	Brain, Spine, knee,ankle, shoulder, and hip	All body parts	It is expanded to all body parts.
Workflow	The software operateson DICOM files,enhances the images,and stores theenhanced images onPACS. Enhancedimages co-exist with theoriginal images.	The software operateson DICOM files,enhances the images,and stores theenhanced images onPACS or on MR device.Enhanced images co-exist with the originalimages.	The enhanced images can also besent to MR device not only toPACS.

{5}------------------------------------------------

Image /page/5/Picture/0 description: The image contains the logo for AIRS MEDICAL. The logo consists of a large, stylized letter "A" in blue, with a curved line extending from the right side of the "A". To the right of the "A" are the words "AIRS" and "MEDICAL" stacked vertically, both in black. The font used for "AIRS MEDICAL" is bold and sans-serif.

VII. PERFORMANCE DATA

SwiftMR, has been assessed and tested and has passed all predetermined testing criteria. The Validation Test Plan was designed to evaluate output functions.

Validation testing indicated that as required by the risk analysis, designated individuals performed all verification and validation activities and that the results demonstrated that the predetermined acceptance criteria were met.

{6}------------------------------------------------

Image /page/6/Picture/0 description: The image contains the logo for AIRS Medical. The logo consists of a large, stylized letter "A" in blue, with a curved line extending from the left side of the "A". To the right of the "A" are the words "AIRS" and "MEDICAL" stacked vertically, both in black, sans-serif font. The logo is simple and modern in design.

The following tests were conducted for SwiftMR:

1. Verification testing: Unit test. Integration/system test conducted. These tests passed.
1. Validation testing: Performance test was conducted using retrospective clinical images for both noise reduction and sharpness increase functions.
- A. For the noise reduction performance, acceptance criteria were defined that the signal-to-noise ratio (SNR) of the SwiftMR-processed image series is increased by 40% or more for at least 90% of the dataset for level 1 with an incremental 1% increase per each level. This test passed.
- B. For the sharpness increase performance, acceptance criteria were defined that the FWHM of a selected region of interest (ROI) is decreased bv 0.13% (deep learning model). 0.43% (filter level 1). 1.7% (filter level 2). 2.3% (filter level 3), 3.6% (filter level 4), 4.5% (filter level 5) or more for at least 90% of the dataset. This test passed.

The validation dataset consists of data of the following conditions:

Manufacturer: SIEMENS, GE, PHILIPS, CANON, ESAOTE, FONAR, FUJIFILM
Field Strength: 0.25T, 0.6T, 1.5T, 3.0T
Anatomical region: Body (breast, abdomen, and pelvis), Cardiac, Neuro (head, neck, and spine), Musculoskeletal (shoulder, wrist, hip, knee, and ankle) 4. Protocol: T1, T2, T2*, FLAIR, PD, DWI, MRA

1. Demographics
age: Adults (22~~93 yrs, 88.4%), Pediatrics (0~~21 yrs, 11.6%)
gender: Male (44.8%), Female (55.2%)
1. Time reduction range for reduced scan time images: up to 50%

To show that the performance of the device is not hindered by site variability, in the validation dataset, we included data from sources not included in the training dataset.

Therefore, it was demonstrated that SwiftMR performance was shown to be substantially equivalent to the predicate device.

VIII. CONCLUSION

The information presented in the 510(k) for SwiftMR contains adequate information, data, and nonclinical test results to demonstrate substantial equivalence to the predicate device. SwiftMR was shown to be substantially equivalent to the predicate device in the areas of technical characteristics, general function, application, and does not raise different questions of safety and effectiveness.

Regulation Number and Section

§ 892.2050 Medical image management and processing system.

(a)
Identification. A medical image management and processing system is a device that provides one or more capabilities relating to the review and digital processing of medical images for the purposes of interpretation by a trained practitioner of disease detection, diagnosis, or patient management. The software components may provide advanced or complex image processing functions for image manipulation, enhancement, or quantification that are intended for use in the interpretation and analysis of medical images. Advanced image manipulation functions may include image segmentation, multimodality image registration, or 3D visualization. Complex quantitative functions may include semi-automated measurements or time-series measurements.(b)
Classification. Class II (special controls; voluntary standards—Digital Imaging and Communications in Medicine (DICOM) Std., Joint Photographic Experts Group (JPEG) Std., Society of Motion Picture and Television Engineers (SMPTE) Test Pattern).